Skip to main content

Research Repository

Advanced Search

Novel gumbel-softmax trick enabled concrete autoencoder with entropy constraints for unsupervised hyperspectral band selection.

Sun, He; Ren, Jinchang; Zhao, Huimin; Yuen, Peter; Tschannerl, Julius

Authors

He Sun

Huimin Zhao

Peter Yuen

Julius Tschannerl



Abstract

As an important topic in hyperspectral image (HSI) analysis, band selection has attracted increasing attention in the last two decades for dimensionality reduction in HSI. With the great success of deep learning (DL)-based models recently, a robust unsupervised band selection (UBS) neural network is highly desired, particularly due to the lack of sufficient ground truth information to train the DL networks. Existing DL models for band selection either depend on the class label information or have unstable results via ranking the learned weights. To tackle these challenging issues, in this article, we propose a Gumbel-Softmax (GS) trick enabled concrete autoencoder-based UBS framework (CAE-UBS) for HSI, in which the learning process is featured by the introduced concrete random variables and the reconstruction loss. By searching from the generated potential band selection candidates from the concrete encoder, the optimal band subset can be selected based on an information entropy (IE) criterion. The idea of the CAE-UBS is quite straightforward, which does not rely on any complicated strategies or metrics. The robust performance on four publicly available datasets has validated the superiority of our CAE-UBS framework in the classification of the HSIs.

Citation

SUN, H., REN, J., ZHAO, H., YUEN, P. and TSCHANNERL, J. 2022. Novel gumbel-softmax trick enabled concrete autoencoder with entropy constraints for unsupervised hyperspectral band selection. IEEE transactions on geoscience and remote sensing [online], 60, article 5506413. Available from: https://doi.org/10.1109/TGRS.2021.3075663

Journal Article Type Article
Acceptance Date Apr 16, 2021
Online Publication Date Jun 4, 2021
Publication Date Jan 12, 2022
Deposit Date Jul 5, 2021
Publicly Available Date Jul 5, 2021
Journal IEEE transactions on geoscience and remote sensing
Print ISSN 0196-2892
Electronic ISSN 1558-0644
Publisher Institute of Electrical and Electronics Engineers (IEEE)
Peer Reviewed Peer Reviewed
Volume 60
Article Number 5506413
DOI https://doi.org/10.1109/TGRS.2021.3075663
Keywords Autoencoder (AE); Concrete random variable; Correlation; Feature extraction; Hyperspectral image (HSI); Hyperspectral imaging; Information entropy (IE); Noise measurement; Principal component analysis; Sun; Training; Unsupervised band selection (UBS)
Public URL https://rgu-repository.worktribe.com/output/1358589

Files

SUN 2022 Novel gumbel-softmax (4.7 Mb)
PDF

Copyright Statement
© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.




You might also like



Downloadable Citations